Capture view (screenshot)

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations set readOnlyHint=false, and the description explains the side effects that justify it: it switches to the 3D window, width/height temporarily resize the 3D window, and images are downscaled to maxSize (default 1600). These are real behavioral facts beyond the annotations. It omits the return payload shape, but the image return is stated.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core purpose, then preparation order, then caveats and examples. Dense but each clause earns its place; the parenthetical cross-references are compact. Slightly long but not padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 11-parameter tool with nested objects and no output schema, the description covers capture target, preparation ordering, defaults (maxSize, format, cropToWindow implied), and the zoom-first caveat for 2D. The absence of an output schema is not a gap since it states the return is an image. Minor omission: no explicit statement about error/permission behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds value the schema cannot: it names the cross-tool field sets ('same fields as open_view', 'same fields as set_3d_view', 'same fields as zoom') and supplies worked examples. The ordering constraint among the nested objects is also semantic information not present in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('saves the ACTIVE Archicad window ... as a picture and returns it as an image') and enumerates the window types covered, which cleanly separates it from siblings like render_view, export_3d_model, and export_pdf. An agent can tell what it produces (an image of the current window) without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear operational context: the optional preparation order (goToView -> view -> threeD -> zoom) and the condition that 2D windows capture at the current zoom, so use zoom {mode:'fit'} first. It does not explicitly exclude alternatives (e.g. render_view for photorealistic output) or state when-not-to-use, which keeps it below a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.